ABSTRACTMoran eigenvector spatial filtering (ESF) approaches have shown promise in accounting for spatial effects in statistical models. Can this extend to machine learning? This article examines the effectiveness of using Moran Eigenvectors as additional spatial features in machine learning models. We generate synthetic datasets with known processes involving spatially varying and nonlinear effects across two different geometries. Moran Eigenvectors calculated from different spatial weights matrices, with and without a priori eigenvector selection, are tested. We assess the performance of popular machine learning models, including Random Forests, LightGBM, XGBoost, and TabNet, and benchmark their accuracies in terms of cross‐validated values against models that use only coordinates as features. We also extract coefficients and functions from the models using GeoShapley and compare them with the true processes. The results show that machine learning models using only location coordinates achieve better accuracies than eigenvector‐based approaches across various experiments and datasets. Furthermore, we discuss that while these findings are relevant for spatial processes that exhibit positive spatial autocorrelation, they do not necessarily apply when modeling network autocorrelation and cases with negative spatial autocorrelation, where Moran Eigenvectors would still be useful.

ABSTRACTThe subject of inequality and its geographical dimensions has seen a surge of interest in recent years. However, existing work tends to study inequality through single spatial scales, even though processes driving inequality operate at and across multiple scales. This article, therefore, investigates how inequality at the regional and local scale relates to phases of economic development in Sweden over three decades. The findings point towards a diverging trend of inequality between the regional and local scale, with a noticeable shift at the turn of the millennium. While the last decades were characterized by a slight regional convergence, inequality at the local scale continued to increase. Accounting for different regional contexts, economic growth and local inequality were most pronounced in the larger urban areas. Surprisingly, though, in the last decade, employment grew in urban areas without an increase in local inequality. In contrast, peripheral and sparsely populated regions experienced a rise in inequality without significant employment growth. This suggests that the link between economic development and inequality is not universal but dependent on, among others, the nature of structural change in the economy and institutional preconditions.

ABSTRACTTraditional spatial interaction (SI) models of migration are susceptible to misspecification when the spatial structure of locations is not properly incorporated. To address this, a novel SI model for migration is introduced that integrates the theories of competing destinations (CD) and intervening opportunities (IO) to capture multiscale spatial structure using the recent generalized additive spatial smoothing (GASS) framework. This GASS CDIO model can identify the appropriate spatial scales to represent the spatial structure of origins and destinations in a data‐driven manner. Validation of the model was conducted through two simulation experiments. The first demonstrates that employing the incorrect scale to capture spatial structure in SI models biases the parameter estimates and increases uncertainty. The second demonstrates that the GASS approach reliably recovers accurate parameters by identifying optimal hyperparameters associated with multiple spatial scales. The GASS CDIO model was then applied to U.S. inter‐county migration data and compared to several other model specifications. The results reveal the unique spatial structure from the perspective of origins and destinations and illustrate the improved recoverability of anticipated migration relationships. This work suggests that the GASS CDIO model better integrates spatial theories of migration and accounts for the multiscale nature of SI processes.

ABSTRACTThe BorealDB dataset provides annual fire and timber harvesting disturbance classifications for Ontario that are derived from a collection of independently classified Landsat scenes. This study assesses the confidence of BorealDB classifications within overlapping scene margins since multiple classifications for common locations are available. For each focal point in BorealDB, the disturbance state of its four nearest spatial orthogonal neighbors were extracted and used to produce classification tree (CT) and random forest (RF) predictions of the focal class. Uncertainty was assessed as being greatest when predictions by neighboring locations or overlapping disturbance classes disagree with the focal class. The assessment found that identified locations of uncertainty within BorealDB varied with disturbance class, with fire having lower uncertainty than timber harvesting. With the results of the analysis, we recommend the inclusion of the analysis outputs and comparisons to supplement existing ensemble confidence attribute in BorealDB.

This study introduces an agent‐based model (ABM) pedestrian simulation tool to assess the risk of close contact (6 feet) in dynamic indoor environments, specifically in urban settings with diverse social activities and spatial structures. Our approach uses machine learning‐based sensitivity analysis (SA) to identify factors impacting the number of individual contacts, such as individual stay time and area. In addition, we conducted an in‐depth quantitative analysis to evaluate how specific factors, such as the strategic placement of obstacles, dwell time, and stay time near the entrances, mitigate the number of contacts. This analysis provides valuable insights for developing practical guidelines to curb contact risks in indoor environments. Lastly, we share the model, validation methods, and associated data as an open‐source Python library, complete with comprehensive documentation. This aims at fostering collaborative research and enables the application of our model across various scenarios, contributing to the development of spatially explicit models. Such efforts enhance the understanding of contact risks in urban indoor settings and promote joint research efforts, thus advancing the field through shared knowledge and tools.

Statistical research on correlation with spatial data dates at least to Student's (W. S. Gosset's) 1914 paper on “the elimination of spurious correlation due to position in time and space.” Since 1968, much of this work has been organized around the concept of spatial autocorrelation (SA). A growing statistical literature is now organized around the concept of “spatial confounding” (SC) but is estranged from, and often at odds with, the SA literature and its history. The SC literature is producing new, sometimes flawed, statistical techniques such as Restricted Spatial Regression (RSR). This article brings the SC literature into conversation with the SA literature and provides a theoretically grounded review of the history of research on correlation with spatial data, explaining some of its implications for the the SC literature. The article builds upon principles of plausible inference to synthesize a guiding theoretical thread that runs throughout the SA literature. This leads to a concise theoretical critique of RSR and a clarification of the logic behind standard spatial‐statistical models.

Rapid urbanization and expansion, stemming from demographic growth and migration from rural areas to urban centers, have heavily strained cities in recent years. These circumstances have created an ever‐growing need for equipment and essential services. On the other hand, previous research has shown that accessibility measurement is a powerful technique for assessing urban compactness. This assessment arises from the willingness of urban planners to develop transport services and land use across various cities globally. This paper addresses the computational problem of spatial accessibility, focusing on the influence of private cars versus public transport. We introduced a metric that enhances the Balanced Floating Catchment Area (BFCA) index. Our metric not only considers multiple transportation modes in the calculation of spatial accessibility but also takes into account variable catchment sizes. We applied our metric in a case study examining spatial accessibility to public hospitals in Casablanca. The results provide a geographic breakdown of each transportation mode, and the accessibility of different scenarios has been compared.

Flows can reflect the spatiotemporal interactions or movements of geographical objects between different locations. Measuring the spatiotemporal autocorrelation of flows can help determine the overall spatiotemporal trends and local patterns. However, quantitative indicators of flows used to measure spatiotemporal autocorrelation both globally and locally are still rare. Therefore, we propose the global and local flow spatiotemporal Moran's I (FSTI). The global FSTI is used to assess the overall spatiotemporal autocorrelation degree of flows, and the local FSTI is applied to identify local spatiotemporal clusters and outliers. In the FSTI, to reflect flow spatiotemporal adjacency relationships, we establish flow spatiotemporal weights by multiplying the spatial and temporal weights of flows considering spatiotemporal orthogonality. The flow spatial weights include contiguity‐based (considering first/higher‐order and common border) and Euclidean distance‐based weights. The temporal weights consider ordinary and lagged cases. As flow attributes may follow a long‐tail distribution, we conduct Monte Carlo simulations to evaluate the statistical significance of the results. We assess the FSTI using synthetic datasets and Chinese population mobility datasets, and compare some results with those of recent flow‐related methods. Additionally, we perform a sensitivity analysis to select a suitable temporal threshold. The results show that the FSTI can be used to effectively detect spatiotemporal variations in the autocorrelation degree and type.